Recognition of arm gestures using multiple orientation sensors: gesture classification

We present a gesture recognition algorithm from Euler angles acquired using multiple orientation sensors. This algorithm is a part of a system for controlling unmanned aerial vehicles (UAVs) in the presence of manned aircrafts on an aircraft deck. After exploring multiple approaches to arm gesture recognition, we investigate a real-time arm gesture recognition system using the IS-300 Pro Precision Motion Tracker by InterSense. Our work consists of (1) analyzing several gesture recognition approaches leading to a selection of an active sensor, (2) gesture modeling using Euler angles, (3) low-level gesture characterization, and (4) model-based gesture classification algorithms. We have implemented and tested the proposed real-time arm gesture recognition system in a laboratory environment with a robot that represents an UAV surrogate.